{"id":"https://openalex.org/W2738778707","doi":"https://doi.org/10.1109/icra.2017.7989202","title":"Information theoretic MPC for model-based reinforcement learning","display_name":"Information theoretic MPC for model-based reinforcement learning","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2738778707","doi":"https://doi.org/10.1109/icra.2017.7989202","mag":"2738778707"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005816849","display_name":"Grady Williams","orcid":"https://orcid.org/0000-0003-1681-9224"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Grady Williams","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010914575","display_name":"Nolan Wagener","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nolan Wagener","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085884369","display_name":"Brian Goldfain","orcid":"https://orcid.org/0000-0003-0754-8354"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Goldfain","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065800861","display_name":"Paul Drews","orcid":"https://orcid.org/0000-0001-8447-880X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Drews","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002228469","display_name":"James M. Rehg","orcid":"https://orcid.org/0000-0003-1793-5462"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James M. Rehg","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110797782","display_name":"Byron Boots","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Boots","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos A. Theodorou","raw_affiliation_strings":["The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"The Institute for Robotics and Intelligent Machines, The Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5005816849"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":28.6394,"has_fulltext":false,"cited_by_count":438,"citation_normalized_percentile":{"value":0.99858614,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1714","last_page":"1721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7836007475852966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7809207439422607},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7800555229187012},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.647986650466919},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.540525496006012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5201330780982971},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5106480717658997},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.46532532572746277},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.4224094748497009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.406907320022583},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2923397421836853},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11361750960350037}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7836007475852966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809207439422607},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7800555229187012},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.647986650466919},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.540525496006012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5201330780982971},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5106480717658997},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.46532532572746277},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.4224094748497009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.406907320022583},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2923397421836853},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11361750960350037},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2017.7989202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1603365166","https://openalex.org/W1925816294","https://openalex.org/W1966514629","https://openalex.org/W1977655452","https://openalex.org/W1994923984","https://openalex.org/W2003132288","https://openalex.org/W2012392077","https://openalex.org/W2027132443","https://openalex.org/W2028678875","https://openalex.org/W2042882799","https://openalex.org/W2065894019","https://openalex.org/W2109169869","https://openalex.org/W2111999018","https://openalex.org/W2117629901","https://openalex.org/W2127107099","https://openalex.org/W2134491302","https://openalex.org/W2134673975","https://openalex.org/W2148112459","https://openalex.org/W2167117957","https://openalex.org/W2167697140","https://openalex.org/W2268617045","https://openalex.org/W2281096776","https://openalex.org/W2410617946","https://openalex.org/W2584986912","https://openalex.org/W2963921033","https://openalex.org/W3005581722","https://openalex.org/W4211089519","https://openalex.org/W4211147054","https://openalex.org/W4285526177","https://openalex.org/W6640290305","https://openalex.org/W6653435097","https://openalex.org/W6676801769"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"We":[0,51],"introduce":[1],"an":[2,73],"information":[3],"theoretic":[4],"model":[5],"predictive":[6],"control":[7],"(MPC)":[8],"algorithm":[9,42,54,82],"capable":[10,84],"of":[11,22,85,90],"handling":[12],"complex":[13],"cost":[14],"criteria":[15],"and":[16,62,92],"general":[17],"nonlinear":[18],"dynamics.":[19],"The":[20],"generality":[21],"the":[23,53,81,100],"approach":[24],"makes":[25],"it":[26],"possible":[27],"to":[28,45],"use":[29],"multi-layer":[30],"neural":[31],"networks":[32],"as":[33,66,68],"dynamics":[34],"models,":[35],"which":[36],"we":[37],"incorporate":[38],"into":[39],"our":[40],"MPC":[41],"in":[43,55,72],"order":[44],"solve":[46],"model-based":[47],"reinforcement":[48],"learning":[49],"tasks.":[50],"test":[52],"simulation":[56],"on":[57,69],"a":[58,87],"cart-pole":[59],"swing":[60],"up":[61],"quadrotor":[63],"navigation":[64],"task,":[65],"well":[67],"actual":[70],"hardware":[71],"aggressive":[74],"driving":[75],"task.":[76],"Empirical":[77],"results":[78],"demonstrate":[79],"that":[80],"is":[83],"achieving":[86],"high":[88],"level":[89],"performance":[91],"does":[93],"so":[94],"only":[95],"utilizing":[96],"data":[97],"collected":[98],"from":[99],"system.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":70},{"year":2023,"cited_by_count":48},{"year":2022,"cited_by_count":61},{"year":2021,"cited_by_count":66},{"year":2020,"cited_by_count":57},{"year":2019,"cited_by_count":54},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":8}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}